{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4JRQ6I3X5AAIQRYQ5FTPOSKGME","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d8ebc5fc6bafb41697f8e1e9656069a8966f2ef3e5f4bd522aa2d6347cf78bac","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-24T12:06:31Z","title_canon_sha256":"e620820a0715a4f31081c2180410ea157cafef1749366d536fe534498399bf0c"},"schema_version":"1.0","source":{"id":"2409.16005","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16005","created_at":"2026-07-05T09:11:03Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16005v1","created_at":"2026-07-05T09:11:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16005","created_at":"2026-07-05T09:11:03Z"},{"alias_kind":"pith_short_12","alias_value":"4JRQ6I3X5AAI","created_at":"2026-07-05T09:11:03Z"},{"alias_kind":"pith_short_16","alias_value":"4JRQ6I3X5AAIQRYQ","created_at":"2026-07-05T09:11:03Z"},{"alias_kind":"pith_short_8","alias_value":"4JRQ6I3X","created_at":"2026-07-05T09:11:03Z"}],"graph_snapshots":[{"event_id":"sha256:1b84dff09c610938d5c6d3a5333dfcebef2d2f202dfec4aa2026b4726e1a7195","target":"graph","created_at":"2026-07-05T09:11:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.16005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The integration of large language models (LLMs) with pre-trained speech models has opened up new avenues in automatic speech recognition (ASR). While LLMs excel in multimodal understanding tasks, effectively leveraging their capabilities for ASR remains a significant challenge. This paper presents a novel training approach to enhance LLM performance in ASR tasks. We propose pre-training LLMs on Pinyin embedding sequences, which represent pronunciation features, to generate corresponding Chinese characters. This step enables the LLM to adapt to generating text from pronunciation features before","authors_text":"Eng Siong Chng, Peng Yizhou, Xionghu Zhong, Yang Yuhang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-24T12:06:31Z","title":"Bridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16005","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:350fd9c4537e9838429276e6537a22182d95bac44653217a6a3140094b255a09","target":"record","created_at":"2026-07-05T09:11:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d8ebc5fc6bafb41697f8e1e9656069a8966f2ef3e5f4bd522aa2d6347cf78bac","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-24T12:06:31Z","title_canon_sha256":"e620820a0715a4f31081c2180410ea157cafef1749366d536fe534498399bf0c"},"schema_version":"1.0","source":{"id":"2409.16005","kind":"arxiv","version":1}},"canonical_sha256":"e2630f2377e800884710e966f74946611adbb3c02920ef97f3efc746a898419c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2630f2377e800884710e966f74946611adbb3c02920ef97f3efc746a898419c","first_computed_at":"2026-07-05T09:11:03.527936Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:03.527936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a0UcWZmPR4trETdFoQkftzb2eTflgzHR4zK9ppC3A63ao+7QARl33r2o3iBn5ZGzHHmGu32o/PKet4fH3gP8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:03.528444Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.16005","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:350fd9c4537e9838429276e6537a22182d95bac44653217a6a3140094b255a09","sha256:1b84dff09c610938d5c6d3a5333dfcebef2d2f202dfec4aa2026b4726e1a7195"],"state_sha256":"abc2860e04573c1f41e0324bcf989f80850f28869f5c7780271ceb8fb584e8a9"}